# sharmaroshan/drugs-recommendation-using-reviews architecture

> Architecture diagram of the GitHub repository sharmaroshan/drugs-recommendation-using-reviews, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2024-12-28). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/sharmaroshan/drugs-recommendation-using-reviews
- Repository: https://github.com/sharmaroshan/drugs-recommendation-using-reviews

## Overview

##### Main Components Identification

The system should be represented as a data pipeline with the following key components:

a) Data Input Layer
- UCI ML Drug Review Dataset (primary data source)
- Optional supplementary datasets
- Data format (reviews, ratings, conditions)

b) Data Processing Layer
- Text preprocessing
- Feature extraction
- Data cleaning and transformation

c) Analysis Modules (represent as parallel components)
- Classification Module (condition prediction)
- Regression Module (rating prediction)
- Sentiment Analysis Module
- Visualization Module

d) Model Layer
- Deep Learning Models
- Training Pipeline
- Evaluation Metrics

##### Component Relationships

- Data flow between components
- Feedback loops for model training
- Input/output relationships
- Dependencies between modules

##### Technical Details

- Data preprocessing pipeline
- Model architecture details
- Evaluation metrics flow
- Visualization pipeline

##### Specific Elements

- Jupyter Notebook integration (referencing DrugsAnalysis.ipynb)
- Documentation flow (connecting to the docs folder structure)
- GitHub integration points

## Diagram (Mermaid)

```mermaid
graph TB
    subgraph Data_Input
        UCI[("UCI ML Drug Review Dataset")]
        SD["Supplementary Datasets"]
        DF["Data Format"]
    end

    subgraph Data_Processing
        TP["Text Preprocessing"]:::processing
        FE["Feature Extraction"]:::processing
        DC["Data Cleaning"]:::processing
    end

    subgraph Analysis_Modules
        CM["Classification Module"]:::analysis
        RM["Regression Module"]:::analysis
        SA["Sentiment Analysis"]:::analysis
        VM["Visualization Module"]:::analysis
    end

    subgraph Model_Layer
        DL["Deep Learning Models"]:::model
        TP_M["Training Pipeline"]:::model
        EM["Evaluation Metrics"]:::model
    end

    subgraph Implementation
        JN["Jupyter Notebook"]:::impl
        PY["Python Utils"]:::impl
        DOC["Documentation"]:::impl
        VC["Version Control"]:::impl
    end

    %% Data Flow
    UCI --> TP
    SD --> TP
    DF --> DC

    TP --> FE
    FE --> DC
    DC --> CM
    DC --> RM
    DC --> SA

    CM --> DL
    RM --> DL
    SA --> DL

    DL --> TP_M
    TP_M --> EM
    EM --> VM

    %% Implementation Connections
    JN --> Analysis_Modules
    PY --> Data_Processing
    DOC --> Implementation
    VC --> Implementation

    %% Styling
    classDef processing fill:#90EE90
    classDef analysis fill:#FFA500
    classDef model fill:#DDA0DD
    classDef impl fill:#ADD8E6

    %% Click Events
    click JN "https://github.com/sharmaroshan/Drugs-Recommendation-using-Reviews/blob/master/DrugsAnalysis.ipynb"
    click PY "https://github.com/sharmaroshan/Drugs-Recommendation-using-Reviews/tree/master//python/"
    click DOC "https://github.com/sharmaroshan/Drugs-Recommendation-using-Reviews/tree/master//docs/"
    click VC "https://github.com/sharmaroshan/Drugs-Recommendation-using-Reviews/tree/master//.github/ISSUE_TEMPLATE/"

    %% Legend
    subgraph Legend
        L1["Processing"]:::processing
        L2["Analysis"]:::analysis
        L3["Model"]:::model
        L4["Implementation"]:::impl
    end
```
